INDEX

Explanations

numerical values and mathematical operations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

doz

-0.16

redo

-0.15

yny

-0.15

iesen

-0.15

 Berm

-0.15

idon

-0.15

cheon

-0.14

 MetroFramework

-0.14

ãİ

-0.14

ibling

-0.14

POSITIVE LOGITS

Tail

0.16

 True

0.15

nat

0.14

}->{

0.14

lif

0.14

 Tail

0.13

CFG

0.13

 åĪ©

0.13

 tail

0.13

etc

0.13

Activations Density 0.015%

numerical values and mathematical operations

No Comments

No Known Activations